US6058366A - Generic run-time engine for interfacing between applications and speech engines - Google Patents

Generic run-time engine for interfacing between applications and speech engines Download PDF

Info

Publication number
US6058366A
US6058366A US09/257,454 US25745499A US6058366A US 6058366 A US6058366 A US 6058366A US 25745499 A US25745499 A US 25745499A US 6058366 A US6058366 A US 6058366A
Authority
US
United States
Prior art keywords
speech
run
time module
data handling
handling system
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
US09/257,454
Inventor
Erik Tarkiainen
Luc Van Tichelen
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nuance Communications Inc
Original Assignee
Lernout and Hauspie Speech Products NV
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Lernout and Hauspie Speech Products NV filed Critical Lernout and Hauspie Speech Products NV
Priority to US09/257,454 priority Critical patent/US6058366A/en
Assigned to LERNOUT & HAUSPIE SPEECH PRODUCTS N.V. reassignment LERNOUT & HAUSPIE SPEECH PRODUCTS N.V. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: TARKIAINEN, FRIK, TICHELEN, LUC VAN
Application granted granted Critical
Publication of US6058366A publication Critical patent/US6058366A/en
Assigned to MICROSOFT CORPORATION reassignment MICROSOFT CORPORATION PATENT LICENSE AGREEMENT Assignors: LERNOUT & HAUSPIE SPEECH PRODUCTS
Assigned to SCANSOFT, INC. reassignment SCANSOFT, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: LERNOUT & HAUSPIE SPEECH PRODUCTS, N.V.
Assigned to NUANCE COMMUNICATIONS, INC. reassignment NUANCE COMMUNICATIONS, INC. MERGER AND CHANGE OF NAME TO NUANCE COMMUNICATIONS, INC. Assignors: SCANSOFT, INC.
Assigned to USB AG, STAMFORD BRANCH reassignment USB AG, STAMFORD BRANCH SECURITY AGREEMENT Assignors: NUANCE COMMUNICATIONS, INC.
Assigned to USB AG. STAMFORD BRANCH reassignment USB AG. STAMFORD BRANCH SECURITY AGREEMENT Assignors: NUANCE COMMUNICATIONS, INC.
Assigned to MITSUBISH DENKI KABUSHIKI KAISHA, AS GRANTOR, NORTHROP GRUMMAN CORPORATION, A DELAWARE CORPORATION, AS GRANTOR, STRYKER LEIBINGER GMBH & CO., KG, AS GRANTOR, ART ADVANCED RECOGNITION TECHNOLOGIES, INC., A DELAWARE CORPORATION, AS GRANTOR, NUANCE COMMUNICATIONS, INC., AS GRANTOR, SCANSOFT, INC., A DELAWARE CORPORATION, AS GRANTOR, SPEECHWORKS INTERNATIONAL, INC., A DELAWARE CORPORATION, AS GRANTOR, DICTAPHONE CORPORATION, A DELAWARE CORPORATION, AS GRANTOR, HUMAN CAPITAL RESOURCES, INC., A DELAWARE CORPORATION, AS GRANTOR, TELELOGUE, INC., A DELAWARE CORPORATION, AS GRANTOR, DSP, INC., D/B/A DIAMOND EQUIPMENT, A MAINE CORPORATON, AS GRANTOR, NOKIA CORPORATION, AS GRANTOR, INSTITIT KATALIZA IMENI G.K. BORESKOVA SIBIRSKOGO OTDELENIA ROSSIISKOI AKADEMII NAUK, AS GRANTOR reassignment MITSUBISH DENKI KABUSHIKI KAISHA, AS GRANTOR PATENT RELEASE (REEL:018160/FRAME:0909) Assignors: MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT
Assigned to ART ADVANCED RECOGNITION TECHNOLOGIES, INC., A DELAWARE CORPORATION, AS GRANTOR, NUANCE COMMUNICATIONS, INC., AS GRANTOR, SCANSOFT, INC., A DELAWARE CORPORATION, AS GRANTOR, SPEECHWORKS INTERNATIONAL, INC., A DELAWARE CORPORATION, AS GRANTOR, DICTAPHONE CORPORATION, A DELAWARE CORPORATION, AS GRANTOR, TELELOGUE, INC., A DELAWARE CORPORATION, AS GRANTOR, DSP, INC., D/B/A DIAMOND EQUIPMENT, A MAINE CORPORATON, AS GRANTOR reassignment ART ADVANCED RECOGNITION TECHNOLOGIES, INC., A DELAWARE CORPORATION, AS GRANTOR PATENT RELEASE (REEL:017435/FRAME:0199) Assignors: MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/30—Creation or generation of source code
    • G06F8/38—Creation or generation of source code for implementing user interfaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output

Definitions

  • the present invention pertains to a task-specialized, application-generic run-time engine for interfacing between a software application program and at least one speech-related application interface.
  • a universal voice-data handling system for interfacing between a software application program and at least one speech-related application interface.
  • the voice-data handling system has a computer and a run-time module, loaded into and running on the computer, adapted to a specialized task for running concurrently and interactively with at least one speech-related application interface. Additionally, the voice-data handling system has an initialization file, loaded into the computer, containing parameters specific to the software application program specifying a behavior of the run-time module.
  • the universal voice-data handling system may also have a data file including information pertinent to the execution of the specialized task by the run-time module.
  • the specialized task may, for example, be at least one of the following group of specialized tasks:
  • a universal voice-data handling system that has a computer and a run-time module, loaded into and running on the computer, adapted to a specialized task for running concurrently and interactively with at least two speech-related application interfaces chosen from the group of an automated speech recognizer, a text-to-speech converter, a speech recorder/player, and a speech-and-music compressor/decompressor.
  • the universal voice-data handling system may also have an application for generating the initialization file which may include a graphic user interface.
  • a software program stored in a digital storage medium which, when loaded into a computer, establishes a run-time module adapted to a specialized task for running concurrently and interactively with at least one speech-related application interface chosen from the group of an automated speech recognizer, a text-to-speech converter, a speech recorder/player, and a speech-and-music compressor/decompressor, and additionally establishes an initialization file containing parameters specific to the software application program for specifying a behavior of the run-time module.
  • FIG. 1 is a block diagram of the interaction between an application program and one or more speech-related application interfaces in accordance with an embodiment of the present invention.
  • FIG. 2 is a block diagram of a configuration for the development of application programs employing one or more speech-related application interfaces in accordance with an embodiment of the present invention.
  • the present invention provides a tool to the developer of a software application program to enable, for example, a computer dialog with a customer regarding a credit card transaction.
  • Many such application programs require calls to engines which handle speech or sound-related functionalities, such as automated speech recognition (ASR) engines, text-to-speech (TTS) engines, speech recording/playback (SRP), speech and music compression/decompression (SMC), speaker verification, language identification, and gender verification engines, for example.
  • ASR automated speech recognition
  • TTS text-to-speech
  • SRP speech recording/playback
  • SMC speech and music compression/decompression
  • speaker verification for example.
  • language identification for example.
  • gender verification engines for example.
  • these engines may generate or recognize particular words in a particular language.
  • a conversational protocol may need to be structured. In the prior art, this function is typically developed as part of the application program.
  • FIG. 1 a schematic diagram is presented of the components of a system, designated generally by numeral 10, which has been configured to employ the current invention.
  • System 10 is to be regarded with complete generality, and no restriction is placed, within the scope of the invention, on the nature of the particular platform on which system 10 is implemented.
  • the various system modules may, in fact, be physically located on different computer platforms.
  • multiple versions of some modules may be implemented, e.g., multiple recognizers for different languages.
  • APIs Application interfaces
  • TTS Transmission Transport Layer
  • SRP SRP
  • SMC engines are shown, with the acronyms having the significance defined above.
  • application program 12 invokes a runtime engine 14 and passes to runtime engine 14 a reference to an initialization file 16.
  • Application program 12 is customized by its developer to provide a specified function. In the course of performing that function, it may be required to solicit information by voice from a person such as a customer.
  • Generation and interpretation of speech are generally conducted by highly specialized engines such as ASR, TTS, SRP and SMC engines, as discussed above.
  • the interaction of the application with each highly specialized engine is typically built into the application by the developer, using a software development kit (SDK), either of a standalone variety geared specifically to particular specialized engines, or a more general toolkit such as an interactive voice response toolkit.
  • SDK software development kit
  • runtime engine (alternatively referred to as a "Speech Wizard” or “Wizard” 14) engenders functionality for conducting certain types of dialogues which are broadly applicable.
  • runtime engine 14 may solicit and retrieve zip code information from a human speaker.
  • General dialog behavior such as handling time-outs, poor recognition, retries, etc., are loaded into the computer platform on which the application is running as part of runtime engine 14.
  • runtime engine 14 provides all the associated grammar information required by the ASR and TTS engines, by generating the grammars, by retrieving the grammar from the initialization file 16 in which the grammar was stored by the Speech Wizard Dialog Builder 22, or by translating or transforming the stored grammar.
  • Runtime engines 14 may also apply specialized information, such as the logic of zip codes. The specialized information may be contained, in part, in the computer code comprising runtime engine 14, or, alternatively or additionally, recourse may be had by runtime engine 14 to a separate data file 18, resident on the computer or electronically accessible, containing further information.
  • Data file 18 may be updatable either by the developer of the application program, by the provider of the Speech Wizard, or by a third-party provider, or by one of their applications residing on the computer in either real-time or off-line.
  • the application developer provides for the requirements of a particular task which the application program requires of the Wizard 14 by building one or more Wizard Initialization files 16 which are created by the application developer and furnished to the user.
  • Wizard initialization file 16 is readily created by the application developer by applying a toolkit described below.
  • Wizard 14 The specifics of the interaction grammar and the speech user interface (SUI) which models the ways people interact by way of voice are contained within Wizard 14 and need not be addressed by the application developer in developing the application. Additionally, postprocessing tasks may be handled by Wizard 14. For example, in the case of soliciting credit card, zip code, or social security numbers, the Wizard, before relaying the information to the application program, may check whether the recognized number is actually a valid response. This information may be used to increase recognition accuracy--i.e., the Wizard may be instructed to relay to the application program the first valid response received via the ASR interface.
  • SAI speech user interface
  • Wizards in accordance with preferred embodiments of the invention, may be implemented in a variety of different modules.
  • Dynamic Menus--The Wizard reads information from a data file at runtime and creates an active vocabulary from the data.
  • the developer simply points to a structured file (i.e. ASCII delimited, ODBC, etc.) That will contain the data to be read at runtime.
  • a structured file i.e. ASCII delimited, ODBC, etc.
  • this Wizard uses phonetic recognition of the spoken word.
  • An alternative embodiment of the invention may reliably handle larger lists (>100).
  • Static Menus--The Wizard reads information from a data file at runtime and creates an active vocabulary from the data. The developer simply enters the words for the vocabulary in the Speech Wizard Dialog Builder, and sets properties for prompts, confirmations, etc. Designed for small to medium lists ( ⁇ 100), this Wizard uses phonetic recognition of the spoken word. An alternative embodiment of the invention may reliably handle larger lists (>100). The developer also has the ability to modify the pronunciation of items in the static menu from within the Speech Wizard Dialog Builder. A shared exception dictionary allows the developer to modify the pronunciation once for recognition and TTS (which is used to confirm the response).
  • the Wizard retrieves a 5 or 9 digit US zip code, using information about the logic of zip codes and a database of valid zip codes to return the best valid recognition result.
  • the zip code data file should be external and readable by the developer, since a preferred embodiment may provide updates to this module via Web site as US zip codes are added and changed. It may also be beneficial to allow the developer to improve recognition further by specifying a range of zip codes--i.e. only zip codes in California. Similar modules may be implemented to handle foreign zip codes.
  • Natural Numbers--The Wizard returns a natural number up to a range specified by the developer, and which is achievable by the recognizer. For example, numbers 1 to 100, where the spoken utterance could be "twenty four", “sixteen”, etc.
  • Alphanumerics--The Wizard returns an alphanumeric string consisting of digits, letters, and symbols (dash, pound, etc.).
  • the developer sets a format string, such as ###@@###, which would represent 3 digits, 2 letters, and 3 digits, with optional dashes.
  • the alphanumeric string is compared against a database provided by the developer, such as a field of part numbers, order numbers, etc.
  • the Wizard returns the top recognition of a 16 digit number, and also the best guess that represents a valid credit card number.
  • Logic algorithms can be used to improve recognition, by recognizing that some recognition results can not be valid credit card numbers. It is important to return both results (best guess and first valid), to allow the application to decide which one to act on (if a caller provides an invalid credit card number, it may not be desirable to substitute the first valid number and take action on it).
  • the Wizard returns a digit matching a formatted string. In this situation it is not necessary to compare against a database, although the Wizard will use confidence levels to confirm the result.
  • the developer is also able to set properties to specify whether to confirm after each digit is spoken, after the string is spoken, or only confirm if the confidence level is low.
  • the Wizard returns the top recognition of a 9 digit social security number, and also the best guess that represents a valid social security number.
  • Logic algorithms can be used to improve recognition, by recognizing that some recognition results can not be valid social security numbers.
  • An option to compare against a database of known caller SS numbers i.e., a student registration system should also be provided.
  • Days--The Wizard returns a day in numeric format based on spoken input.
  • the utterance could be "Next Tuesday”, “yesterday”, “tomorrow”, etc.
  • Dates--The Wizard returns a day/month/year in numeric format based on spoken input.
  • the utterance could be "January twenty fourth", “one twenty four”, etc.
  • Confirmation Wizard The Wizard returns an affirmative or negative response based on spoken input, which could include "Yes”, “No", “OK”, “No, thank you”, or similar possible responses.
  • Reading Wizard The Wizard reads a text file, specified at design time or run time by the developer, such as an e-mail message, a news story, directions to an office, etc.
  • the Wizard listens for and interprets spoken commands such as "Previous Sentence”, “Repeat Message”, etc. to allow the caller to navigate through the message.
  • Address Wizard goes through all steps of asking for a street address (zip code, street name, number, city, state, telephone number);
  • Form Filling Wizard similar to address wizard, but the fields may be configured by the developer (whereas for the address wizard the fields such as street, state etc. have been predefined). The wizard may attempt to fill fields marked as required, while filling optional fields with information if spoken by the user;
  • Password Wizard to obtain a password through DTMF or potentially even speaker verification
  • SQL Wizard to process queries to a database (e.g. by means of SQL) stated in natural language;
  • User Word Wizard to create a list of words trained by the user for creation of specific lists or customized commands
  • Times Wizard similar to the day and dates wizard
  • Speak Wizard the simplest of all, just speaks a message without expecting any speech input (no ASR or DTMF), useful for announcement phrases.
  • Speech Wizard Dialog Builder 22 is itself a graphic user interface (GUI) which prompts the application program developer to select specific Wizards and to set the desired properties by graphic interaction. For example, the developer might set the types of valid credit cards and to prompt for the expiration date, etc.
  • GUI graphic user interface

Abstract

A universal voice-data handling system for interfacing between a software application program and at least one speech-related application interface. The voice-data handling system includes a computer system; a run-time module, loaded into and running on the computer system, the run-time module adapted to a specialized task for running concurrently and interactively with the at least one speech-related application interface; and an initialization file, loaded into the computer system, containing parameters specific to the software application program the initialization file being generated by an application, based on the behavior required by the speech-related software application program for specifying a behavior of the run-time module in relation to the software application program the initialization file being generated by an application, based on the behavior required by the speech-related software application program.

Description

This application claims the benefit of U.S. Provisional Application No. 60/075,907, filed Feb. 25, 1998, and U.S. Provisional Application No. 60/076,634, filed Mar. 3, 1998.
TECHNICAL FIELD
The present invention pertains to a task-specialized, application-generic run-time engine for interfacing between a software application program and at least one speech-related application interface.
BACKGROUND OF THE INVENTION
The operation of software application programs which employ speech recognition or text-to-speech (TTS) features generally requires that the application program interact with engines, typically though not necessarily resident on the platform on which the application program is running, which perform automatic speech recognition (ASR) or TTS functions. This interaction between the application and ASR or TTS engines occurs via application interfaces (APIs) and requires that the application program itself generate the particular calls and protocol required by the APIs. It is desirable to obviate the development effort required to program the low-level interaction between the application program and the ASR or TTS engines, since much of this interaction involves functionalities common across many applications.
SUMMARY OF THE INVENTION
In accordance with one aspect of the invention, in one of its embodiments, there is provided a universal voice-data handling system for interfacing between a software application program and at least one speech-related application interface. The voice-data handling system has a computer and a run-time module, loaded into and running on the computer, adapted to a specialized task for running concurrently and interactively with at least one speech-related application interface. Additionally, the voice-data handling system has an initialization file, loaded into the computer, containing parameters specific to the software application program specifying a behavior of the run-time module.
In accordance with alternate embodiments of the present invention, the universal voice-data handling system may also have a data file including information pertinent to the execution of the specialized task by the run-time module. Although a wide range of specialized tasks may be implemented, the specialized task may, for example, be at least one of the following group of specialized tasks:
a. querying a person to obtain an affirmation/negation response;
b. querying a person to obtain calendric information;
c. prompting a person to select from a menu;
d. querying a person to obtain payment information;
e. reading text to a person and responding to clarification queries;
f. querying a person to obtain address information;
g. querying a person to obtain information for data fields in an application specific form;
h. prompting a person to provide a password;
i. querying a person to process queries to a database;
j. prompting a person to create a list of words selected for creation of specific lists or customized commands;
k. querying a person to obtain temporal information;
l. querying a person to obtain measurement information; and
m. providing a spoken announcement message.
In accordance with another embodiment of the present invention, there is provided a universal voice-data handling system that has a computer and a run-time module, loaded into and running on the computer, adapted to a specialized task for running concurrently and interactively with at least two speech-related application interfaces chosen from the group of an automated speech recognizer, a text-to-speech converter, a speech recorder/player, and a speech-and-music compressor/decompressor.
In any of the aforementioned embodiments, the universal voice-data handling system may also have an application for generating the initialization file which may include a graphic user interface.
In accordance with a further embodiment of the present invention, there is provided a software program stored in a digital storage medium which, when loaded into a computer, establishes a run-time module adapted to a specialized task for running concurrently and interactively with at least one speech-related application interface chosen from the group of an automated speech recognizer, a text-to-speech converter, a speech recorder/player, and a speech-and-music compressor/decompressor, and additionally establishes an initialization file containing parameters specific to the software application program for specifying a behavior of the run-time module.
BRIEF DESCRIPTION OF THE DRAWINGS
The invention will be more readily understood by reference to the following description, taken with the accompanying drawings, in which:
FIG. 1 is a block diagram of the interaction between an application program and one or more speech-related application interfaces in accordance with an embodiment of the present invention; and
FIG. 2 is a block diagram of a configuration for the development of application programs employing one or more speech-related application interfaces in accordance with an embodiment of the present invention.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
The present invention provides a tool to the developer of a software application program to enable, for example, a computer dialog with a customer regarding a credit card transaction. Many such application programs require calls to engines which handle speech or sound-related functionalities, such as automated speech recognition (ASR) engines, text-to-speech (TTS) engines, speech recording/playback (SRP), speech and music compression/decompression (SMC), speaker verification, language identification, and gender verification engines, for example. These engines may generate or recognize particular words in a particular language. However, in order to gather or impart information to a customer, a conversational protocol may need to be structured. In the prior art, this function is typically developed as part of the application program.
Referring to FIG. 1, a schematic diagram is presented of the components of a system, designated generally by numeral 10, which has been configured to employ the current invention. System 10 is to be regarded with complete generality, and no restriction is placed, within the scope of the invention, on the nature of the particular platform on which system 10 is implemented. In some embodiments, the various system modules may, in fact, be physically located on different computer platforms. Likewise, multiple versions of some modules may be implemented, e.g., multiple recognizers for different languages. Application interfaces (APIs) to ASR, TTS, SRP and SMC engines are shown, with the acronyms having the significance defined above.
During operation of system 10, application program 12 invokes a runtime engine 14 and passes to runtime engine 14 a reference to an initialization file 16. Application program 12 is customized by its developer to provide a specified function. In the course of performing that function, it may be required to solicit information by voice from a person such as a customer. Generation and interpretation of speech are generally conducted by highly specialized engines such as ASR, TTS, SRP and SMC engines, as discussed above. The interaction of the application with each highly specialized engine is typically built into the application by the developer, using a software development kit (SDK), either of a standalone variety geared specifically to particular specialized engines, or a more general toolkit such as an interactive voice response toolkit.
Certain tasks have a general applicability in computer telephony. In accordance with the present invention, runtime engine (alternatively referred to as a "Speech Wizard" or "Wizard" 14) engenders functionality for conducting certain types of dialogues which are broadly applicable. For example, runtime engine 14 may solicit and retrieve zip code information from a human speaker. General dialog behavior, such as handling time-outs, poor recognition, retries, etc., are loaded into the computer platform on which the application is running as part of runtime engine 14. Additionally, runtime engine 14 provides all the associated grammar information required by the ASR and TTS engines, by generating the grammars, by retrieving the grammar from the initialization file 16 in which the grammar was stored by the Speech Wizard Dialog Builder 22, or by translating or transforming the stored grammar. Runtime engines 14 may also apply specialized information, such as the logic of zip codes. The specialized information may be contained, in part, in the computer code comprising runtime engine 14, or, alternatively or additionally, recourse may be had by runtime engine 14 to a separate data file 18, resident on the computer or electronically accessible, containing further information. Data file 18 may be updatable either by the developer of the application program, by the provider of the Speech Wizard, or by a third-party provider, or by one of their applications residing on the computer in either real-time or off-line.
The application developer provides for the requirements of a particular task which the application program requires of the Wizard 14 by building one or more Wizard Initialization files 16 which are created by the application developer and furnished to the user. Wizard initialization file 16 is readily created by the application developer by applying a toolkit described below.
The specifics of the interaction grammar and the speech user interface (SUI) which models the ways people interact by way of voice are contained within Wizard 14 and need not be addressed by the application developer in developing the application. Additionally, postprocessing tasks may be handled by Wizard 14. For example, in the case of soliciting credit card, zip code, or social security numbers, the Wizard, before relaying the information to the application program, may check whether the recognized number is actually a valid response. This information may be used to increase recognition accuracy--i.e., the Wizard may be instructed to relay to the application program the first valid response received via the ASR interface.
Wizards, in accordance with preferred embodiments of the invention, may be implemented in a variety of different modules.
Menu Wizards:
Dynamic Menus--The Wizard reads information from a data file at runtime and creates an active vocabulary from the data. The developer simply points to a structured file (i.e. ASCII delimited, ODBC, etc.) That will contain the data to be read at runtime. Designed for small to medium lists (<100), this Wizard uses phonetic recognition of the spoken word. An alternative embodiment of the invention may reliably handle larger lists (>100).
Static Menus--The Wizard reads information from a data file at runtime and creates an active vocabulary from the data. The developer simply enters the words for the vocabulary in the Speech Wizard Dialog Builder, and sets properties for prompts, confirmations, etc. Designed for small to medium lists (<100), this Wizard uses phonetic recognition of the spoken word. An alternative embodiment of the invention may reliably handle larger lists (>100). The developer also has the ability to modify the pronunciation of items in the static menu from within the Speech Wizard Dialog Builder. A shared exception dictionary allows the developer to modify the pronunciation once for recognition and TTS (which is used to confirm the response).
Number Wizards:
Zip Codes--The Wizard retrieves a 5 or 9 digit US zip code, using information about the logic of zip codes and a database of valid zip codes to return the best valid recognition result. The zip code data file should be external and readable by the developer, since a preferred embodiment may provide updates to this module via Web site as US zip codes are added and changed. It may also be beneficial to allow the developer to improve recognition further by specifying a range of zip codes--i.e. only zip codes in California. Similar modules may be implemented to handle foreign zip codes.
Natural Numbers--The Wizard returns a natural number up to a range specified by the developer, and which is achievable by the recognizer. For example, numbers 1 to 100, where the spoken utterance could be "twenty four", "sixteen", etc.
Alphanumerics--The Wizard returns an alphanumeric string consisting of digits, letters, and symbols (dash, pound, etc.). The developer sets a format string, such as ###@@###, which would represent 3 digits, 2 letters, and 3 digits, with optional dashes. The alphanumeric string is compared against a database provided by the developer, such as a field of part numbers, order numbers, etc.
Credit Cards--The Wizard returns the top recognition of a 16 digit number, and also the best guess that represents a valid credit card number. Logic algorithms can be used to improve recognition, by recognizing that some recognition results can not be valid credit card numbers. It is important to return both results (best guess and first valid), to allow the application to decide which one to act on (if a caller provides an invalid credit card number, it may not be desirable to substitute the first valid number and take action on it).
Formatted Digits--Similar to alphanumerics, the Wizard returns a digit matching a formatted string. In this situation it is not necessary to compare against a database, although the Wizard will use confidence levels to confirm the result. The developer is also able to set properties to specify whether to confirm after each digit is spoken, after the string is spoken, or only confirm if the confidence level is low.
Social Security Number--The Wizard returns the top recognition of a 9 digit social security number, and also the best guess that represents a valid social security number. Logic algorithms can be used to improve recognition, by recognizing that some recognition results can not be valid social security numbers. An option to compare against a database of known caller SS numbers (i.e., a student registration system) should also be provided.
In addition, we recognized as a result of the survey that barge-in support is important, and that digit recognition should always be offered in parallel with a DTMF option--the Speech Wizard should return a digit string regardless of whether or not the digits were spoken or pressed on the keypad. The option of barge-in support and the availability of DTMF as an alternative is not specific to the number wizards, but applies to all wizards.
Calendar Wizards:
Days--The Wizard returns a day in numeric format based on spoken input. The utterance could be "Next Tuesday", "yesterday", "tomorrow", etc.
Dates--The Wizard returns a day/month/year in numeric format based on spoken input. The utterance could be "January twenty fourth", "one twenty four", etc. Confirmation Wizard: The Wizard returns an affirmative or negative response based on spoken input, which could include "Yes", "No", "OK", "No, thank you", or similar possible responses.
Reading Wizard: The Wizard reads a text file, specified at design time or run time by the developer, such as an e-mail message, a news story, directions to an office, etc. The Wizard listens for and interprets spoken commands such as "Previous Sentence", "Repeat Message", etc. to allow the caller to navigate through the message.
Address Wizard: goes through all steps of asking for a street address (zip code, street name, number, city, state, telephone number);
Form Filling Wizard: similar to address wizard, but the fields may be configured by the developer (whereas for the address wizard the fields such as street, state etc. have been predefined). The wizard may attempt to fill fields marked as required, while filling optional fields with information if spoken by the user;
Password Wizard: to obtain a password through DTMF or potentially even speaker verification;
SQL Wizard: to process queries to a database (e.g. by means of SQL) stated in natural language;
User Word Wizard: to create a list of words trained by the user for creation of specific lists or customized commands;
Times Wizard: similar to the day and dates wizard;
Weight, Length, Speed Etc. Wizards: for other specific measurement units
Speak Wizard: the simplest of all, just speaks a message without expecting any speech input (no ASR or DTMF), useful for announcement phrases.
Alternative embodiments of the present invention may implement other Wizard modules.
Development of the application program interaction with the Speech Wizard 14 is described with reference to FIG. 2. The developer employs a toolkit 20 to select specific Wizards (such as a credit card or natural number wizard, etc.) and to set the properties for behavior of a specific Wizard. The properties which are set for behavior of a specific Wizard reside as parameters in Wizard initialization file 16. Toolkit 20 invokes a Speech Wizard Dialog Builder 22 (shown in FIG. 1) which is independent of the particular toolkit employed, thus the developer may use any available speech development toolkit which supports the Speech Wizard Dialog Builder. In a preferred embodiment, Speech Wizard Dialog Builder 22 is itself a graphic user interface (GUI) which prompts the application program developer to select specific Wizards and to set the desired properties by graphic interaction. For example, the developer might set the types of valid credit cards and to prompt for the expiration date, etc.
The described embodiments of the invention are intended to be merely exemplary and numerous variations and modifications will be apparent to those skilled in the art. All such variations and modifications are intended to be within the scope of the present invention as defined in the appended claims.

Claims (19)

We claim:
1. A universal voice-data handling system for interfacing between a software application program and at least one speech-related application interface, the voice-data handling system comprising:
a. a computer system;
b. a run-time module, loaded into and running on the computer system, the run-time module adapted to a specialized task for running concurrently and interactively with the at least one speech-related application interface;
c. an initialization file, loaded into the computer system, containing parameters specific to the software application program for specifying a behavior of the run-time module in relation to the software application program; and
d. an application for generating the initialization file based on the behavior required by the software application program.
2. A universal voice-data handling system according to claim 1, further comprising a data file including information pertinent to execution of the specialized task by the run-time module.
3. A universal voice-data handling system according to claim 1, wherein the specialized task includes at least one of the group of:
a. querying a person to obtain an affirmation/negation response;
b. querying a person to obtain calendric information;
c. prompting a person to select from a menu;
d. querying a person to obtain payment information;
e. reading text to a person and responding to clarification queries;
f. querying a person to obtain address information;
g. querying a person to obtain information for data fields in an application-specific form;
h. prompting a person to provide a password;
i. querying a person to process queries to a database;
j. prompting a person to create a list of words selected for creation of specific lists or customized commands;
k. querying a person to obtain temporal information;
l. querying a person to obtain measurement information; and
m. providing a spoken announcement message.
4. A universal voice-data handling system according to claim 1, wherein the application for generating the initialization file includes a graphic user interface.
5. A universal voice-data handling system according to claim 1, in which the run-time module and the initialization file are resident on a single computer platform.
6. A universal voice-data handling system according to claim 5, in which the speech-related application interfaces are resident on the same computer platform as the run-time module and the initialization file.
7. A universal voice-data handling system according to claim 5, in which the speech-related application interfaces are resident on a different computer platform from the run-time module and the initialization file.
8. A universal voice-data handling system according to claim 1, in which the run-time module and the initialization file are resident on different computer platforms.
9. A universal voice-data handling system according to claim 8, in which the speech-related application interfaces are resident on the same computer platform as either the run-time module or the initialization file.
10. A universal voice-data handling system according to claim 8, in which the speech-related application interfaces are resident on a different computer platform from either the run-time module or the initialization file.
11. A universal voice-data handling system comprising:
a. a computer system;
b. a run-time module, loaded into and running on the computer system, the run-time module adapted to a specialized task for running concurrently and interactively with at least two speech-related application interfaces chosen from the group of an automated speech recognizer, a text-to-speech converter, a speech recorder/player, a speech-and-music compressor/decompressor, speaker verification, language identification, and gender verification;
c. an initialization file, loaded into the computer system, containing parameters specific to the software application program for specifying a behavior of the run-time module in relation to the software application program; and
d. an application for generating the initialization file based on the behavior required by the software application program.
12. A universal voice-data handling system according to claim 11, wherein the application for generating the initialization file includes a graphic user interface.
13. A universal voice-data handling system according to claim 11, in which the run-time module and the initialization file are resident on a single computer platform.
14. A universal voice-data handling system according to claim 13, in which the speech-related application interfaces are resident on the same computer platform as the run-time module and the initialization file.
15. A universal voice-data handling system according to claim 13, in which the speech-related application interfaces are resident on a different computer platform from the run-time module and the initialization file.
16. A universal voice-data handling system according to claim 11, in which the run-time module and the initialization file are resident on different computer platforms.
17. A universal voice-data handling system according to claim 16, in which the speech-related application interfaces are resident on the same computer platform as either the run-time module or the initialization file.
18. A universal voice-data handling system according to claim 16, in which the speech-related application interfaces are resident on a different computer platform from either the run-time module or the initialization file.
19. A software program stored in a digital storage medium, the program, when loaded into a computer system, establishing:
a. a run-time module adapted to a specialized task for running concurrently and interactively with at least one speech-related application interface chosen from the group of an automated speech recognizer, a text-to-speech converter, a speech recorder/player, a speech-and-music compressor/decompressor, speaker verification, language identification, and gender verification, the software program;
b. an initialization file containing parameters specific to the software application program for specifying a behavior of the run-time module; and
c. an application for generating the initialization file based on the behavior required by the software application program.
US09/257,454 1998-02-25 1999-02-25 Generic run-time engine for interfacing between applications and speech engines Expired - Lifetime US6058366A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US09/257,454 US6058366A (en) 1998-02-25 1999-02-25 Generic run-time engine for interfacing between applications and speech engines

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US7590798P 1998-02-25 1998-02-25
US7663498P 1998-03-03 1998-03-03
US09/257,454 US6058366A (en) 1998-02-25 1999-02-25 Generic run-time engine for interfacing between applications and speech engines

Publications (1)

Publication Number Publication Date
US6058366A true US6058366A (en) 2000-05-02

Family

ID=26757418

Family Applications (1)

Application Number Title Priority Date Filing Date
US09/257,454 Expired - Lifetime US6058366A (en) 1998-02-25 1999-02-25 Generic run-time engine for interfacing between applications and speech engines

Country Status (6)

Country Link
US (1) US6058366A (en)
EP (1) EP1057099A1 (en)
JP (1) JP2002505460A (en)
AU (1) AU2789499A (en)
CA (1) CA2319002A1 (en)
WO (1) WO1999044118A1 (en)

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6246986B1 (en) * 1998-12-31 2001-06-12 At&T Corp. User barge-in enablement in large vocabulary speech recognition systems
US20020026317A1 (en) * 2000-06-17 2002-02-28 Alcatel Process and spoken announcement module for outputting a spoken announcement and a program module therefor
US6480580B1 (en) * 1998-09-24 2002-11-12 Ericsson Inc. User addressable computer telephony system
US20020180789A1 (en) * 2001-06-01 2002-12-05 Gregory Guttmann Framework for developing web-based and email-based collaborative programs
US20030056025A1 (en) * 2001-09-17 2003-03-20 Dean Moses Method and system for sharing different web components between different web sites in a portal framework
US20030115057A1 (en) * 2001-12-13 2003-06-19 Junqua Jean-Claude Constraint-based speech recognition system and method
US20030144846A1 (en) * 2002-01-31 2003-07-31 Denenberg Lawrence A. Method and system for modifying the behavior of an application based upon the application's grammar
US20030158731A1 (en) * 2002-02-15 2003-08-21 Falcon Stephen Russell Word training interface
KR100432373B1 (en) * 2001-11-07 2004-05-24 주식회사 아이엔커넥트 The voice recognition system for independent speech processing
US20040111259A1 (en) * 2002-12-10 2004-06-10 Miller Edward S. Speech recognition system having an application program interface
US20050273339A1 (en) * 2004-06-02 2005-12-08 Chaudhari Upendra V Method and apparatus for remote command, control and diagnostics of systems using conversational or audio interface
US20060069573A1 (en) * 2002-02-04 2006-03-30 Microsoft Corporation Speech controls for use with a speech system
US20060074652A1 (en) * 2004-09-20 2006-04-06 International Business Machines Corporation Method and system for voice-enabled autofill
US7043426B2 (en) 1998-04-01 2006-05-09 Cyberpulse, L.L.C. Structured speech recognition
US20060106612A1 (en) * 1998-05-01 2006-05-18 Ben Franklin Patent Holding Llc Voice user interface with personality
US20060161429A1 (en) * 2002-02-04 2006-07-20 Microsoft Corporation Systems And Methods For Managing Multiple Grammars in a Speech Recognition System
US20070078657A1 (en) * 2000-07-20 2007-04-05 Microsoft Corporation Middleware layer between speech related applications and engines
US20070192109A1 (en) * 2006-02-14 2007-08-16 Ivc Inc. Voice command interface device
US7299185B2 (en) 2002-02-04 2007-11-20 Microsoft Corporation Systems and methods for managing interactions from multiple speech-enabled applications
US20080154591A1 (en) * 2005-02-04 2008-06-26 Toshihiro Kujirai Audio Recognition System For Generating Response Audio by Using Audio Data Extracted
US20100191519A1 (en) * 2009-01-28 2010-07-29 Microsoft Corporation Tool and framework for creating consistent normalization maps and grammars
US20110202344A1 (en) * 2010-02-12 2011-08-18 Nuance Communications Inc. Method and apparatus for providing speech output for speech-enabled applications
US20120010875A1 (en) * 2002-11-28 2012-01-12 Nuance Communications Austria Gmbh Classifying text via topical analysis, for applications to speech recognition
US8332226B1 (en) * 2005-01-07 2012-12-11 At&T Intellectual Property Ii, L.P. System and method of dynamically modifying a spoken dialog system to reduce hardware requirements
US8374879B2 (en) 2002-02-04 2013-02-12 Microsoft Corporation Systems and methods for managing interactions from multiple speech-enabled applications
US8606916B2 (en) 2001-09-17 2013-12-10 Open Text S.A. Graphical user interface for performing administration on web components of web sites in a portal framework
US10474837B2 (en) 2006-12-22 2019-11-12 Open Text Corporation Access control for business process data
CN115086418A (en) * 2022-07-22 2022-09-20 浙江中控技术股份有限公司 Data transmission method, data transmission device and electronic equipment

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0218904A2 (en) * 1985-10-15 1987-04-22 International Business Machines Corporation Process for modifying operation of application program
US5255305A (en) * 1990-11-01 1993-10-19 Voiceplex Corporation Integrated voice processing system
WO1995001597A2 (en) * 1993-07-01 1995-01-12 British Telecomm System for generating instructions for speech application
US5546586A (en) * 1993-05-06 1996-08-13 Apple Computer, Inc. Method and apparatus for vectorizing the contents of a read only memory device without modifying underlying source code
US5666534A (en) * 1993-06-29 1997-09-09 Bull Hn Information Systems Inc. Method and appartus for use by a host system for mechanizing highly configurable capabilities in carrying out remote support for such system
US5835913A (en) * 1995-11-21 1998-11-10 Texas Instruments Incorporated System and method for reproducing files of software information
US5890163A (en) * 1996-09-26 1999-03-30 Compaq Computer Corp Sharing an electronic mail message with a party not named as a recipient of the message

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0218904A2 (en) * 1985-10-15 1987-04-22 International Business Machines Corporation Process for modifying operation of application program
US4755932A (en) * 1985-10-15 1988-07-05 International Business Machines Corporation Interpreter program for providing commands to a computer application program
US5255305A (en) * 1990-11-01 1993-10-19 Voiceplex Corporation Integrated voice processing system
US5452341A (en) * 1990-11-01 1995-09-19 Voiceplex Corporation Integrated voice processing system
US5546586A (en) * 1993-05-06 1996-08-13 Apple Computer, Inc. Method and apparatus for vectorizing the contents of a read only memory device without modifying underlying source code
US5666534A (en) * 1993-06-29 1997-09-09 Bull Hn Information Systems Inc. Method and appartus for use by a host system for mechanizing highly configurable capabilities in carrying out remote support for such system
WO1995001597A2 (en) * 1993-07-01 1995-01-12 British Telecomm System for generating instructions for speech application
US5835913A (en) * 1995-11-21 1998-11-10 Texas Instruments Incorporated System and method for reproducing files of software information
US5890163A (en) * 1996-09-26 1999-03-30 Compaq Computer Corp Sharing an electronic mail message with a party not named as a recipient of the message

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
"Application programing Interface for Speech Recognition System", IBM Technical Disclosure Bulletin, vol. 36, No. 6B, Jun. 1, 1993, pp. 11-12.
Application programing Interface for Speech Recognition System , IBM Technical Disclosure Bulletin , vol. 36, No. 6B, Jun. 1, 1993, pp. 11 12. *
Victor W. Zue, "Navigating the Information Superhighway Using Spoken Language Interfaces," IEEE Expert, pp. 39-43, Oct. 1995.
Victor W. Zue, Navigating the Information Superhighway Using Spoken Language Interfaces, IEEE Expert, pp. 39 43, Oct. 1995. *

Cited By (65)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7043426B2 (en) 1998-04-01 2006-05-09 Cyberpulse, L.L.C. Structured speech recognition
US9055147B2 (en) 1998-05-01 2015-06-09 Intellectual Ventures I Llc Voice user interface with personality
US7266499B2 (en) 1998-05-01 2007-09-04 Ben Franklin Patent Holding Llc Voice user interface with personality
US20080103777A1 (en) * 1998-05-01 2008-05-01 Ben Franklin Patent Holding Llc Voice User Interface With Personality
US20060106612A1 (en) * 1998-05-01 2006-05-18 Ben Franklin Patent Holding Llc Voice user interface with personality
US6480580B1 (en) * 1998-09-24 2002-11-12 Ericsson Inc. User addressable computer telephony system
US6246986B1 (en) * 1998-12-31 2001-06-12 At&T Corp. User barge-in enablement in large vocabulary speech recognition systems
US20020026317A1 (en) * 2000-06-17 2002-02-28 Alcatel Process and spoken announcement module for outputting a spoken announcement and a program module therefor
US20070078657A1 (en) * 2000-07-20 2007-04-05 Microsoft Corporation Middleware layer between speech related applications and engines
US7379874B2 (en) * 2000-07-20 2008-05-27 Microsoft Corporation Middleware layer between speech related applications and engines
US20020180789A1 (en) * 2001-06-01 2002-12-05 Gregory Guttmann Framework for developing web-based and email-based collaborative programs
US9716751B2 (en) 2001-09-17 2017-07-25 Open Text Sa Ulc Method and system for sharing web components between web sites
US9521046B2 (en) 2001-09-17 2016-12-13 Open Text Sa Ulc System and method for provisioning user access to web site components in a portal framework
US9037739B2 (en) 2001-09-17 2015-05-19 Open Text S.A. Method and system for sharing different web components between different web sites in a portal framework
US7293070B2 (en) 2001-09-17 2007-11-06 Vignette Corporation Method and system for deploying web components between portals in a portal framework
US8606916B2 (en) 2001-09-17 2013-12-10 Open Text S.A. Graphical user interface for performing administration on web components of web sites in a portal framework
US8407353B2 (en) 2001-09-17 2013-03-26 Open Text S.A. Method and system for sharing different web components between different web sites in a portal framework
US9749411B2 (en) 2001-09-17 2017-08-29 Open Text Sa Ulc Method and system for sharing different web components between different web sites in a portal framework
US20030056026A1 (en) * 2001-09-17 2003-03-20 Ed Anuff Graphical user interface for performing administration on web components of web sites in a portal framework
US20100274812A1 (en) * 2001-09-17 2010-10-28 Dean Moses Method and System for Sharing Different Web Components Between Different Web Sites in a Portal Framework
US7801990B2 (en) 2001-09-17 2010-09-21 Vignette Software Llc Graphical user interface for performing administration on web components of web sites in a portal framework
US20030056025A1 (en) * 2001-09-17 2003-03-20 Dean Moses Method and system for sharing different web components between different web sites in a portal framework
KR100432373B1 (en) * 2001-11-07 2004-05-24 주식회사 아이엔커넥트 The voice recognition system for independent speech processing
US20030115057A1 (en) * 2001-12-13 2003-06-19 Junqua Jean-Claude Constraint-based speech recognition system and method
US7124085B2 (en) * 2001-12-13 2006-10-17 Matsushita Electric Industrial Co., Ltd. Constraint-based speech recognition system and method
US20030144846A1 (en) * 2002-01-31 2003-07-31 Denenberg Lawrence A. Method and system for modifying the behavior of an application based upon the application's grammar
US7742925B2 (en) 2002-02-04 2010-06-22 Microsoft Corporation Speech controls for use with a speech system
US20060069573A1 (en) * 2002-02-04 2006-03-30 Microsoft Corporation Speech controls for use with a speech system
US7363229B2 (en) 2002-02-04 2008-04-22 Microsoft Corporation Systems and methods for managing multiple grammars in a speech recognition system
US8660843B2 (en) 2002-02-04 2014-02-25 Microsoft Corporation Management and prioritization of processing multiple requests
US20060106617A1 (en) * 2002-02-04 2006-05-18 Microsoft Corporation Speech Controls For Use With a Speech System
US7720678B2 (en) 2002-02-04 2010-05-18 Microsoft Corporation Systems and methods for managing multiple grammars in a speech recognition system
US7299185B2 (en) 2002-02-04 2007-11-20 Microsoft Corporation Systems and methods for managing interactions from multiple speech-enabled applications
US8447616B2 (en) 2002-02-04 2013-05-21 Microsoft Corporation Systems and methods for managing multiple grammars in a speech recognition system
US20100191529A1 (en) * 2002-02-04 2010-07-29 Microsoft Corporation Systems And Methods For Managing Multiple Grammars in a Speech Recognition System
US20060161429A1 (en) * 2002-02-04 2006-07-20 Microsoft Corporation Systems And Methods For Managing Multiple Grammars in a Speech Recognition System
US7254545B2 (en) 2002-02-04 2007-08-07 Microsoft Corporation Speech controls for use with a speech system
US8374879B2 (en) 2002-02-04 2013-02-12 Microsoft Corporation Systems and methods for managing interactions from multiple speech-enabled applications
US20030158731A1 (en) * 2002-02-15 2003-08-21 Falcon Stephen Russell Word training interface
US7587317B2 (en) * 2002-02-15 2009-09-08 Microsoft Corporation Word training interface
US8612209B2 (en) * 2002-11-28 2013-12-17 Nuance Communications, Inc. Classifying text via topical analysis, for applications to speech recognition
US20120010875A1 (en) * 2002-11-28 2012-01-12 Nuance Communications Austria Gmbh Classifying text via topical analysis, for applications to speech recognition
US10923219B2 (en) 2002-11-28 2021-02-16 Nuance Communications, Inc. Method to assign word class information
US10515719B2 (en) 2002-11-28 2019-12-24 Nuance Communications, Inc. Method to assign world class information
US9996675B2 (en) 2002-11-28 2018-06-12 Nuance Communications, Inc. Method to assign word class information
US8965753B2 (en) 2002-11-28 2015-02-24 Nuance Communications, Inc. Method to assign word class information
US20040111259A1 (en) * 2002-12-10 2004-06-10 Miller Edward S. Speech recognition system having an application program interface
US20050273339A1 (en) * 2004-06-02 2005-12-08 Chaudhari Upendra V Method and apparatus for remote command, control and diagnostics of systems using conversational or audio interface
US8224649B2 (en) * 2004-06-02 2012-07-17 International Business Machines Corporation Method and apparatus for remote command, control and diagnostics of systems using conversational or audio interface
US7953597B2 (en) * 2004-09-20 2011-05-31 Nuance Communications, Inc. Method and system for voice-enabled autofill
US20060074652A1 (en) * 2004-09-20 2006-04-06 International Business Machines Corporation Method and system for voice-enabled autofill
US8600757B2 (en) * 2005-01-07 2013-12-03 At&T Intellectual Property Ii, L.P. System and method of dynamically modifying a spoken dialog system to reduce hardware requirements
US8332226B1 (en) * 2005-01-07 2012-12-11 At&T Intellectual Property Ii, L.P. System and method of dynamically modifying a spoken dialog system to reduce hardware requirements
US20080154591A1 (en) * 2005-02-04 2008-06-26 Toshihiro Kujirai Audio Recognition System For Generating Response Audio by Using Audio Data Extracted
US20090222270A2 (en) * 2006-02-14 2009-09-03 Ivc Inc. Voice command interface device
US20070192109A1 (en) * 2006-02-14 2007-08-16 Ivc Inc. Voice command interface device
US10474837B2 (en) 2006-12-22 2019-11-12 Open Text Corporation Access control for business process data
US8990088B2 (en) 2009-01-28 2015-03-24 Microsoft Corporation Tool and framework for creating consistent normalization maps and grammars
US20100191519A1 (en) * 2009-01-28 2010-07-29 Microsoft Corporation Tool and framework for creating consistent normalization maps and grammars
US20150106101A1 (en) * 2010-02-12 2015-04-16 Nuance Communications, Inc. Method and apparatus for providing speech output for speech-enabled applications
US20110202344A1 (en) * 2010-02-12 2011-08-18 Nuance Communications Inc. Method and apparatus for providing speech output for speech-enabled applications
US9424833B2 (en) * 2010-02-12 2016-08-23 Nuance Communications, Inc. Method and apparatus for providing speech output for speech-enabled applications
US8949128B2 (en) * 2010-02-12 2015-02-03 Nuance Communications, Inc. Method and apparatus for providing speech output for speech-enabled applications
CN115086418A (en) * 2022-07-22 2022-09-20 浙江中控技术股份有限公司 Data transmission method, data transmission device and electronic equipment
CN115086418B (en) * 2022-07-22 2022-12-27 浙江中控技术股份有限公司 Data transmission method, data transmission device and electronic equipment

Also Published As

Publication number Publication date
AU2789499A (en) 1999-09-15
WO1999044118A1 (en) 1999-09-02
CA2319002A1 (en) 1999-09-02
EP1057099A1 (en) 2000-12-06
JP2002505460A (en) 2002-02-19

Similar Documents

Publication Publication Date Title
US6058366A (en) Generic run-time engine for interfacing between applications and speech engines
US7869998B1 (en) Voice-enabled dialog system
US7451089B1 (en) System and method of spoken language understanding in a spoken dialog service
US6937983B2 (en) Method and system for semantic speech recognition
US8645122B1 (en) Method of handling frequently asked questions in a natural language dialog service
US7505906B2 (en) System and method for augmenting spoken language understanding by correcting common errors in linguistic performance
US11869495B2 (en) Voice to voice natural language understanding processing
US20030144846A1 (en) Method and system for modifying the behavior of an application based upon the application&#39;s grammar
US10468016B2 (en) System and method for supporting automatic speech recognition of regional accents based on statistical information and user corrections
US20050137868A1 (en) Biasing a speech recognizer based on prompt context
US20020072914A1 (en) Method and apparatus for creation and user-customization of speech-enabled services
US8457973B2 (en) Menu hierarchy skipping dialog for directed dialog speech recognition
US9412364B2 (en) Enhanced accuracy for speech recognition grammars
CN111402862A (en) Voice recognition method, device, storage medium and equipment
USH2187H1 (en) System and method for gender identification in a speech application environment
US20040019488A1 (en) Email address recognition using personal information
US20040034532A1 (en) Filter architecture for rapid enablement of voice access to data repositories
Callejas et al. Implementing modular dialogue systems: A case of study
US7054813B2 (en) Automatic generation of efficient grammar for heading selection
Sharman Speech interfaces for computer systems: Problems and potential
Wu et al. Intelligent Call Manager Based on the Integration of Computer Telephony, Internet and Speech Processing
Freitas Interface de Fala para Dispositivos Móveis

Legal Events

Date Code Title Description
AS Assignment

Owner name: LERNOUT & HAUSPIE SPEECH PRODUCTS N.V., BELGIUM

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:TARKIAINEN, FRIK;TICHELEN, LUC VAN;REEL/FRAME:009932/0420

Effective date: 19990423

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: MICROSOFT CORPORATION, WASHINGTON

Free format text: PATENT LICENSE AGREEMENT;ASSIGNOR:LERNOUT & HAUSPIE SPEECH PRODUCTS;REEL/FRAME:012539/0977

Effective date: 19970910

AS Assignment

Owner name: SCANSOFT, INC., MASSACHUSETTS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:LERNOUT & HAUSPIE SPEECH PRODUCTS, N.V.;REEL/FRAME:012775/0308

Effective date: 20011212

REMI Maintenance fee reminder mailed
REMI Maintenance fee reminder mailed
FPAY Fee payment

Year of fee payment: 4

SULP Surcharge for late payment
AS Assignment

Owner name: NUANCE COMMUNICATIONS, INC., MASSACHUSETTS

Free format text: MERGER AND CHANGE OF NAME TO NUANCE COMMUNICATIONS, INC.;ASSIGNOR:SCANSOFT, INC.;REEL/FRAME:016914/0975

Effective date: 20051017

AS Assignment

Owner name: USB AG, STAMFORD BRANCH,CONNECTICUT

Free format text: SECURITY AGREEMENT;ASSIGNOR:NUANCE COMMUNICATIONS, INC.;REEL/FRAME:017435/0199

Effective date: 20060331

Owner name: USB AG, STAMFORD BRANCH, CONNECTICUT

Free format text: SECURITY AGREEMENT;ASSIGNOR:NUANCE COMMUNICATIONS, INC.;REEL/FRAME:017435/0199

Effective date: 20060331

AS Assignment

Owner name: USB AG. STAMFORD BRANCH,CONNECTICUT

Free format text: SECURITY AGREEMENT;ASSIGNOR:NUANCE COMMUNICATIONS, INC.;REEL/FRAME:018160/0909

Effective date: 20060331

Owner name: USB AG. STAMFORD BRANCH, CONNECTICUT

Free format text: SECURITY AGREEMENT;ASSIGNOR:NUANCE COMMUNICATIONS, INC.;REEL/FRAME:018160/0909

Effective date: 20060331

FPAY Fee payment

Year of fee payment: 8

FPAY Fee payment

Year of fee payment: 12

AS Assignment

Owner name: INSTITIT KATALIZA IMENI G.K. BORESKOVA SIBIRSKOGO

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: SPEECHWORKS INTERNATIONAL, INC., A DELAWARE CORPOR

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: DSP, INC., D/B/A DIAMOND EQUIPMENT, A MAINE CORPOR

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: NOKIA CORPORATION, AS GRANTOR, FINLAND

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: ART ADVANCED RECOGNITION TECHNOLOGIES, INC., A DEL

Free format text: PATENT RELEASE (REEL:017435/FRAME:0199);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0824

Effective date: 20160520

Owner name: DICTAPHONE CORPORATION, A DELAWARE CORPORATION, AS

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: STRYKER LEIBINGER GMBH & CO., KG, AS GRANTOR, GERM

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: NUANCE COMMUNICATIONS, INC., AS GRANTOR, MASSACHUS

Free format text: PATENT RELEASE (REEL:017435/FRAME:0199);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0824

Effective date: 20160520

Owner name: DSP, INC., D/B/A DIAMOND EQUIPMENT, A MAINE CORPOR

Free format text: PATENT RELEASE (REEL:017435/FRAME:0199);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0824

Effective date: 20160520

Owner name: ART ADVANCED RECOGNITION TECHNOLOGIES, INC., A DEL

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: TELELOGUE, INC., A DELAWARE CORPORATION, AS GRANTO

Free format text: PATENT RELEASE (REEL:017435/FRAME:0199);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0824

Effective date: 20160520

Owner name: DICTAPHONE CORPORATION, A DELAWARE CORPORATION, AS

Free format text: PATENT RELEASE (REEL:017435/FRAME:0199);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0824

Effective date: 20160520

Owner name: NUANCE COMMUNICATIONS, INC., AS GRANTOR, MASSACHUS

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: MITSUBISH DENKI KABUSHIKI KAISHA, AS GRANTOR, JAPA

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: SCANSOFT, INC., A DELAWARE CORPORATION, AS GRANTOR

Free format text: PATENT RELEASE (REEL:017435/FRAME:0199);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0824

Effective date: 20160520

Owner name: TELELOGUE, INC., A DELAWARE CORPORATION, AS GRANTO

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: SCANSOFT, INC., A DELAWARE CORPORATION, AS GRANTOR

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: HUMAN CAPITAL RESOURCES, INC., A DELAWARE CORPORAT

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520

Owner name: SPEECHWORKS INTERNATIONAL, INC., A DELAWARE CORPOR

Free format text: PATENT RELEASE (REEL:017435/FRAME:0199);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0824

Effective date: 20160520

Owner name: NORTHROP GRUMMAN CORPORATION, A DELAWARE CORPORATI

Free format text: PATENT RELEASE (REEL:018160/FRAME:0909);ASSIGNOR:MORGAN STANLEY SENIOR FUNDING, INC., AS ADMINISTRATIVE AGENT;REEL/FRAME:038770/0869

Effective date: 20160520